Martin Boyanov·May 20, 2024Let’s Build Bg2Vec: Apply LLM2Vec on BgGPTWith the advent of RAG and text generation solutions, it is of utmost importance to have a model which can extract meaningful…
Martin Boyanov·Sep 11, 2021K-means clustering for faster collaborative filteringThe classical collaborative filtering approach includes computing the cosine distance between all pairs of users or items. In the book…
Martin Boyanov·May 16, 2021K-means Clustering for Vote AnalysisOn the 4th April 2021 we held elections in Bulgaria to choose the new parliament. This article will attempt to apply K-means clustering on…
Martin Boyanov·May 27, 201972 от сутрин до вечерНапоследък чета доста Edward Tufte в опити да си увелича data viz скиловете. Идеята е, че освен красиви, графиките трябва да са и полезни…
InCommetricbyMartin Boyanov·Apr 19, 2019Semi-Frozen Embeddings for NLP Transfer LearningFinetuning only domain-specific words to reduce overfitting
InCommetricbyMartin Boyanov·Mar 21, 2019Detecting Near-Duplicates in the NewsOverview and benchmark of data science methods for duplicate detectionA response icon1A response icon1
Martin Boyanov·Dec 5, 2018Forward & Backward Character Language Models for Conjoined Word Separation with fast.aiConjoined words are words that wrongly consist of two words. We’ll try to split them up to increase the data quality.A response icon1A response icon1
Martin Boyanov·Sep 9, 2018Embeddings Transformations for Sentiment Lexicon EnrichmentThere exists a vector v, such that translating a negative word n by v leads to the vicinity of the antonym of n.
InBecoming Human: Artificial Intelligence MagazinebyMartin Boyanov·Feb 1, 2018Neural Style TransferSurviving the Game Jam without artists